Journal of Digital Imaging

, Volume 14, Supplement 1, pp 214–216 | Cite as

Using rigid motion constraints for the registration of free-form surfaces

Scientific Posters and Demonstrations

Abstract

We present a new method for registration of free-form surfaces based on the iterative closest point (ICPI method and on geometric properties of reflected correspondence vectors. The method is based on computing relative gaps between reflected correspondences and between the projections of reflected correspondences along the rotation axis and using these to eliminate false matches. Experimental results on synthetic data and on real range images demonstrate that the method is robust and accurate for image registration with small motions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Besl PJ, McKay NO: A method for registration of 3D shapes. IEEE Trans PAMI 14:239–256, 1992Google Scholar
  2. 2.
    Zhang Z: Iterative point matching for registration of free-form curves.INRIA Technical Report no. 1658, May 1992Google Scholar
  3. 3.
    Feldmar J, Ayache N, Betting F: 3D-2D projective registration of free-form curves and surfaces. Computer Vision Image Understand 65:403–424, 1997CrossRefGoogle Scholar
  4. 4.
    Liu Y, Rodrigues MA: Analysing the geometric properties of reflected correspondence vectors for the registration of free form shapes. Proc 2000 IEEE Int Conf Systems, Man, and Cybernetics (SMC’OO), 2000, pp 1501–1506Google Scholar
  5. 5.
    Golub GH, Van Loan CF: Matrix Computations, (ed 3). Baltimore, MD, John Hopkins University Press, 1996Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2001

Authors and Affiliations

  • Yonghuai Liu
    • 1
    • 2
  • Marcos A. Rodrigues
    • 1
    • 2
  • Baogang Wei
    • 1
    • 2
  1. 1.Computing Research Centre, School of ComputingSheffield Hallam UniversitySheffieldUK
  2. 2.Department of Computer ScienceZhejiang UniversityHangzhouChina

Personalised recommendations